decision-debate
Run a formal multi-perspective debate on one contested MEL/SRHR design decision: persona agents mapped to real specialist lenses research the call independently and blind, debate one round, then a decision-memo-shaped synthesis keeps agreements and genuine disagreements visible for Ane to decide on. Use when Ane cannot decide between named options and wants independent perspectives argued. Token-heavy by design: reserve for real decisions. Not for sharpening a design she already leans on (/grill-mel), net-new builds (brainstorming), or a plain options paper (/decision-memo), and never for building anything.
- Installs
- 356
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/gasserane/personal-skills --skill decision-debate- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads decision-debate automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Decision-debate (MEL/SRHR)
A formal debate that brings independent perspectives TO Ane on one contested MEL/SRHR design call. It operationalises the CLAUDE.md three-perspective rule: several agents research the same decision from different lenses, argue once, and the result is synthesised for Ane to decide on. It decides nothing itself.
Lane — when this skill, not another
The grill family differs by direction, not topic:
- decision-debate (this): brings perspectives to Ane. Independent agents research and argue a contested call Ane did not answer herself. Use only when the answer is genuinely uncertain and reasonable experts would disagree.
- /grill-mel: pulls from Ane. Interviews her one question at a time to sharpen a design she already leans on.
- brainstorming (superpowers): for net-new builds headed to a code spec.
Reserved for genuine, consequential, contested decisions. Never for building. If the answer is already known, use /grill-mel or /ann. If the task is to produce a deliverable, use /ann.
Gate before running
Confirm two things before spawning agents, because this is token-heavy:
- The decision is genuinely contested (reasonable experts would split), not just unfamiliar to Ane.
- It is a decision, not a build or a deliverable.
If either fails, stop and route to /grill-mel, /ann, or brainstorming.
Method — three stages
State the decision in one sentence, confirm it with Ane, then run:
Stage 1 — independent, blind research
- Pick the personas. 3 by default, 5 for a high-stakes call. Each persona maps to a real specialist lens from
agent-improvements/agent_registry.md, not an invented character. The default trio:- Method (evaluation-design / contribution-plausibility stance): what can the evidence actually carry?
- Political economy and decolonial (political-economy-reviewer stance): whose knowledge counts, what power sits in the data?
- Operational feasibility (ma-priorities / reader-position stance): can the people on the ground do this, and does it serve the MA? For a 5-persona run, add the two lenses most load-bearing for the specific call (for example gender-transformative, safeguarding, or a costing/efficiency lens).
- Spawn the personas in a single message so they run in parallel (the Vi parallel fan-out mechanism). Each gets the same decision brief but a different lens mandate, and researches independently and blind to the others using WebSearch, the knowledge MCP, and the MEL Wiki.
- Each persona returns: its position, its one load-bearing reason, and the evidence behind it. Apply the citation standard. Flag any unsourced fact with
⚠️rather than inventing it.
Stage 2 — one debate round
Give each persona the others' Stage 1 positions. Each writes a short rebuttal: where it concedes, where it holds, and why. One round only. No endless back-and-forth.
Stage 3 — synthesis Ane decides on
Write one readable Tier 1 brief in the decision-memo shape:
- Context — the decision in one sentence and why it is contested.
- Options — each live option with its strongest case, drawn from the personas.
- Points of agreement — where the personas converged.
- Genuine disagreements — kept visible, not smoothed over. This is the value of the debate.
- Recommendation — the recommended option, with the dissent recorded next to it.
- Risks and reversibility — what the recommendation costs and how hard it is to undo.
The no-write gate
The debate decides nothing. The synthesis ends with this exact line:
DECISION REQUIRED, this is a recommendation not a decision.
The skill writes nothing to any canonical file: no wiki edit, no registry change, no committed document. It returns the brief to Ane and stops. Ane decides; acting on the decision is a separate step she takes.
Scale escalation
For an unusually large debate where deterministic token control matters, run the same three stages through the Workflow tool's judge-panel/parallel pattern instead: parallel persona agents in Stage 1, a debate stage, a synthesis stage, with budget bounding the spend. The Workflow route needs explicit opt-in each time; this skill is the routable default.
Close
Hand Ane the synthesis brief and stop. Do not adopt the recommendation, edit any file, or start building. If Ane decides and wants the decision acted on, that is a fresh task for /ann or the right builder skill.
FAQ
What does the decision-debate skill do?
Run a formal multi-perspective debate on one contested MEL/SRHR design decision: persona agents mapped to real specialist lenses research the call independently and blind, debate one round, then a decision-memo-shaped synthesis keeps agreements and genuine disagreements visible for Ane to decide on. Use when Ane cannot decide between named options and wants independent perspectives argued. Token-heavy by design: reserve for real decisions. Not for sharpening a design she already leans on (/grill-mel), net-new builds (brainstorming), or a plain options paper (/decision-memo), and never for building anything.
How do I install decision-debate?
Run npx skills add https://github.com/gasserane/personal-skills --skill decision-debate in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/decision-debate/ (personal) or .claude/skills/decision-debate/ (project).
Which AI agents can use decision-debate?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is decision-debate safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains decision-debate?
It is published by gasserane in gasserane/personal-skills. It has 356 recorded installs.
More from gasserane/personal-skills
journal-reflection
gasserane/personal-skills
Guide Ane through structured reflection at end of day, end of week, after a decision, or after new learning material, producing Obsidian-compatible markdown and writing to the vault journal when the path is reachable. Use on 'journal', 'reflect on today', 'weekly review', 'after-action review', or asks that reference writing to the Obsidian vault. For a quick 4-line post-deliverable capture use /learned instead.
evidence-synthesis
gasserane/personal-skills
Conduct a rigorous rapid evidence assessment or systematic-lite literature review for MEL/SRHR questions. Use when Ane asks for "evidence review", "literature review", "evidence synthesis", "REA", "what does the evidence say", "what do we know about", or similar. Produces a structured brief with question framing, method, findings by theme, confidence grading, and implications for programme or evaluation design. Does not invent citations.
daily-brief
gasserane/personal-skills
Produce a scannable morning briefing for Ane (Senior MEL/SRHR Specialist at IPPF). Use when the user asks for "daily brief", "morning briefing", "start of day", "what's on today", "plan my day", or similar. Assembles today's priority, calendar, overdue items, pending decisions, and an energy check. Operates on user-provided inputs by default; richer when calendar/email MCP servers are connected.
decision-memo
gasserane/personal-skills
Draft a structured decision memo for Ane. Use when the user asks for a "decision memo", "decision doc", "options paper", "recommendation brief", or equivalent. Produces a scannable document with context, options, recommendation, risks, and reversibility. Applies Ane's CLAUDE.md writing style automatically.
video-content-analysis
gasserane/personal-skills
Convert FGD/webinar/SBCC video files into a structured artefact pack (transcript, frames, manifest, Tier 1 BLUF summary) the existing MEL specialists can consume. Use when Ane asks to "analyse a video", "transcribe a focus group", "process a webinar recording", "summarise a meeting recording", or runs /analyze-video . Tiered transcription (local Whisper for sensitive; M365 Stream for internal/public). Privacy + consent validated by construction. Per-run feedback prompt feeds the self-improvement loop.
power-bi-build
gasserane/personal-skills
Build IPPF-branded Power BI artefacts from analytical input. Use when Ane asks to build, scaffold, or update a Power BI dashboard, semantic model, DAX measures, or .pbip project. Applies IPPF Visual Identity 2025 brand, MEL-standard DAX measures, and three standard page recipes (indicator dashboard, equity disaggregation, methodology card). Requires the pbi CLI (pbi-cli-tool, command name pbi) installed and Power BI Desktop running with a .pbip open.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。